For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
S
Sagar Seth

Sagar Seth

Fine-tuning LLMs for NL-to-ELK Query Generation

India flagChennai, India
$20.00/hrExpertOther

Key Skills

Software

Other

Top Subject Matter

Natural language processing
query generation
LLM fine-tuning

Top Data Types

TextText
ImageImage

Top Task Types

Fine-tuningFine-tuning
Object DetectionObject Detection
ClassificationClassification
Text GenerationText Generation
Text SummarizationText Summarization
Function CallingFunction Calling
Computer Programming/CodingComputer Programming/Coding
Question AnsweringQuestion Answering
Bounding BoxBounding Box

Freelancer Overview

Fine-tuning LLMs for NL-to-ELK Query Generation. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Technology, Sri Sivasubramaniya Nadar College of Engineering (Anna University) (2023) and Master of Technology, Indian Institute of Information Technology Guwahati (2023). AI-training focus includes data types such as Text and Image and labeling workflows including Fine-tuning and Object Detection.

ExpertEnglish

Labeling Experience

YOLOv8 Data Annotation and Fine-tuning for Object Detection

OtherImageObject Detection
Fine-tuned the YOLOv8 model for object detection and classification tasks on a custom image dataset. Focused on accurately annotating and labeling bounding boxes for four distinct classes to achieve high model precision. Addressed post-labeling performance using model conversion and deployment strategies for optimized inference. • Ensured consistent and precise bounding box annotation across the dataset. • Maintained class definition quality and data balance for robust training. • Utilized model performance metrics to iterate on labeling completeness. • Coordinated labeling and annotation workflow with downstream deployment processes.

Fine-tuned the YOLOv8 model for object detection and classification tasks on a custom image dataset. Focused on accurately annotating and labeling bounding boxes for four distinct classes to achieve high model precision. Addressed post-labeling performance using model conversion and deployment strategies for optimized inference. • Ensured consistent and precise bounding box annotation across the dataset. • Maintained class definition quality and data balance for robust training. • Utilized model performance metrics to iterate on labeling completeness. • Coordinated labeling and annotation workflow with downstream deployment processes.

2023 - Present

Fine-tuning LLMs for NL-to-ELK Query Generation

OtherTextFine Tuning
Conducted fine-tuning of Flan-T5 and CodeLlama models for natural language to ELK query translation. Evaluated model accuracy using a custom 'LLM-as-a-judge' pipeline to ensure generation quality for domain-specific applications. Oversaw the end-to-end ML pipeline for training and validation, reducing manual query authoring effort substantially. • Implemented process included supervised labeling of text queries and target outputs. • Used best practices for high-quality, human-guided model updates and validation. • Automated evaluation workflows emphasized output accuracy and label consistency. • Labeling efforts focused on training data quality, annotation completeness, and reproducibility.

Conducted fine-tuning of Flan-T5 and CodeLlama models for natural language to ELK query translation. Evaluated model accuracy using a custom 'LLM-as-a-judge' pipeline to ensure generation quality for domain-specific applications. Oversaw the end-to-end ML pipeline for training and validation, reducing manual query authoring effort substantially. • Implemented process included supervised labeling of text queries and target outputs. • Used best practices for high-quality, human-guided model updates and validation. • Automated evaluation workflows emphasized output accuracy and label consistency. • Labeling efforts focused on training data quality, annotation completeness, and reproducibility.

2023 - Present

Education

S

Sri Sivasubramaniya Nadar College of Engineering (Anna University)

Bachelor of Technology, Information Technology

Bachelor of Technology
2019 - 2023
I

Indian Institute of Information Technology Guwahati

Master of Technology, Computer Science and Engineering

Master of Technology
2023

Work History

C

Comcast

Machine Learning Engineer

Chennai
2023 - Present